NORMA eResearch @NCI Library

Prediction of Optimal Virtual Machine Allocation and Migration using Machine Learning

Arokiaraj, Richard Selvaraj (2024) Prediction of Optimal Virtual Machine Allocation and Migration using Machine Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (402kB) | Preview

Abstract

The primary objective of this research is to utilize machine learning techniques in order to make predictions for optimal allocation and migration strategy of virtual machines (VMs) in cloud environments. The exploitation of cloud resources, in particular virtual machines (VMs), is an essential component in maximizing performance, optimization of resource utilization, and optimizing of cost. Manual allocation and migration decisions can be difficult to make because of the changing patterns of workload and the complicated configurations of the system. This research provides a comparative case study of two machine learning alogrithms, Long Short-Term Memory and Q-learning reinforcement learning algorithm upon which algorithm provides the most optimal allocation and migration strategy. A comprehensive computational environment is set up with EC2 instances and S3 storage. Using the tools such as TensorFlow and PySpark, various models are created. Data is collected, processed and analyzed, and evaluated using metrics such as the LSTM accuracy and recall, and the effectiveness of Q-learning is determined on a reward-base validity defined. The following comparative analysis of both methods demonstrates the implications of both approaches and their contribution to improving efficiency in terms of cloud resource management operations.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Arun, Shreyas Setlur
UNSPECIFIED
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Cloud computing
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Ciara O'Brien
Date Deposited: 03 Jul 2025 08:54
Last Modified: 03 Jul 2025 08:54
URI: https://norma.ncirl.ie/id/eprint/8008

Actions (login required)

View Item View Item